Research Scientist Intern - Video Generation (AI)

Location: Mountain View, United States; Workplace type: Onsite

Compensation: $50–$80 per hour in Mountain View

Company

hirify.global develops games and entertainment content, including Genshin Impact, Honkai: Star Rail, and Zenless Zone Zero, while researching game development technologies and immersive virtual world experiences.

What you will do

• Research, develop, and implement post-training methods for large-scale video generation models, including supervised fine-tuning, preference optimization, and reinforcement learning.
• Develop controllable video generation techniques for motion control, camera movement, trajectory following, action-conditioned generation, and interactive video generation.
• Design and conduct experiments targeting video quality, temporal consistency, motion realism, and alignment with user instructions.
• Collaborate with research and engineering teams on training pipelines, evaluation benchmarks, and scalable experimentation workflows.
• Track advances in video generation and generative AI and contribute to research publications and practical applications.

Requirements

• Currently pursuing a Master's or PhD in Computer Science, Artificial Intelligence, Computer Vision, Machine Learning, or a related technical field.
• Strong research background and hands-on experience training or fine-tuning video generative models.
• Solid understanding of generative modeling techniques, including diffusion models, flow matching, Diffusion Transformers, and autoregressive models.
• Strong proficiency in Python and deep learning frameworks such as PyTorch.
• Ability to independently implement research ideas, conduct experiments, analyze results, and collaborate effectively with a research team.

Nice to have

• Publications at top-tier AI and computer vision conferences, especially first-author publications related to video generation or controllable video generation.
• Research experience in camera control, motion control, trajectory-guided generation, action-conditioned generation, or interactive video generation.
• Experience with large-scale video model training, distributed training, or training and inference optimization.
• Contributions to influential open-source video generation projects or research implementations.

Culture & Benefits

• Onsite internship based in Mountain View.
• Hourly compensation varies based on location, knowledge, skills, and experience.
• Inclusive environment focused on diverse backgrounds and immersive virtual world experiences.